Sciweavers

1440 search results - page 230 / 288
» Warped Gaussian Processes
Sort
View
IJCNLP
2005
Springer
15 years 3 months ago
Regularisation Techniques for Conditional Random Fields: Parameterised Versus Parameter-Free
Recent work on Conditional Random Fields (CRFs) has demonstrated the need for regularisation when applying these models to real-world NLP data sets. Conventional approaches to regu...
Andrew Smith, Miles Osborne
NOLISP
2005
Springer
15 years 3 months ago
MLP Internal Representation as Discriminative Features for Improved Speaker Recognition
Feature projection by non-linear discriminant analysis (NLDA) can substantially increase classification performance. In automatic speech recognition (ASR) the projection provided b...
Dalei Wu, Andrew C. Morris, Jacques C. Koreman
AUSAI
2004
Springer
15 years 3 months ago
A Dynamic Allocation Method of Basis Functions in Reinforcement Learning
In this paper, we propose a dynamic allocation method of basis functions, an Allocation/Elimination Gaussian Softmax Basis Function Network (AE-GSBFN), that is used in reinforcemen...
Shingo Iida, Kiyotake Kuwayama, Masayoshi Kanoh, S...
BIOADIT
2004
Springer
15 years 3 months ago
Explaining Low-Level Brightness-Contrast Illusions Using Disinhibition
Conventional Difference of Gaussian (DOG) filter is usually used to model the early stage of visual processing. However, convolution operation used with DOG does not explicitly a...
Yingwei Yu, Takashi Yamauchi, Yoonsuck Choe
ICIAP
2001
Springer
15 years 2 months ago
A Neurodynamical Retinal Network Based on Reaction-Diffusion Systems
A dynamical model for retinal processing is presented. The model describes the output of retinal ganglion cells whose receptive field is composed of a center and a surround combi...
Matthias S. Keil, Gabriel Cristóbal, Heiko ...